Information Theory and Machine Learning

The recent successes of machine learning, especially regarding systems based on deep neural networks, have encouraged further research activities and raised a new set of challenges in understanding and designing complex machine learning algorithms. New applications require learning algorithms to be...

ver descrição completa

Na minha lista:
Detalhes bibliográficos
Formato: Online
Idioma:inglês
Publicado em: MDPI - Multidisciplinary Digital Publishing Institute 2022
Assuntos:
Acesso em linha:ONIX_20221025_9783036553078_107
Tags: Adicionar Tag
Sem tags, seja o primeiro a adicionar uma tag!
_version_ 1869515219666993152
collection Directory of Open Access Books
description The recent successes of machine learning, especially regarding systems based on deep neural networks, have encouraged further research activities and raised a new set of challenges in understanding and designing complex machine learning algorithms. New applications require learning algorithms to be distributed, have transferable learning results, use computation resources efficiently, convergence quickly on online settings, have performance guarantees, satisfy fairness or privacy constraints, incorporate domain knowledge on model structures, etc. A new wave of developments in statistical learning theory and information theory has set out to address these challenges. This Special Issue, "Machine Learning and Information Theory", aims to collect recent results in this direction reflecting a diverse spectrum of visions and efforts to extend conventional theories and develop analysis tools for these complex machine learning systems.
format Online
id doab-20.500.12854ir-93254
institution Directory of Open Access Books
language eng
publishDate 2022
publishDateRange 2022
publishDateSort 2022
publisher MDPI - Multidisciplinary Digital Publishing Institute
publisherStr MDPI - Multidisciplinary Digital Publishing Institute
record_format ojs
spelling doab-20.500.12854ir-932542024-04-09T23:15:55Z Information Theory and Machine Learning Zheng, Lizhong Tian, Chao supervised classification independent and non-identically distributed features analytical error probability empirical risk generalization error K-means clustering model compression population risk rate distortion theory vector quantization overfitting information criteria entropy model-based clustering merging mixture components component overlap interpretability time series prediction finite state machines hidden Markov models recurrent neural networks reservoir computers long short-term memory deep neural network information theory local information geometry feature extraction spiking neural network meta-learning information theoretic learning minimum error entropy artificial general intelligence closed-loop transcription linear discriminative representation rate reduction minimax game fairness HGR maximal correlation independence criterion separation criterion pattern dictionary atypicality Lempel–Ziv algorithm lossless compression anomaly detection information-theoretic bounds distribution and federated learning thema EDItEUR::T Technology, Engineering, Agriculture, Industrial processes::TB Technology: general issues thema EDItEUR::T Technology, Engineering, Agriculture, Industrial processes::TB Technology: general issues::TBX History of engineering and technology The recent successes of machine learning, especially regarding systems based on deep neural networks, have encouraged further research activities and raised a new set of challenges in understanding and designing complex machine learning algorithms. New applications require learning algorithms to be distributed, have transferable learning results, use computation resources efficiently, convergence quickly on online settings, have performance guarantees, satisfy fairness or privacy constraints, incorporate domain knowledge on model structures, etc. A new wave of developments in statistical learning theory and information theory has set out to address these challenges. This Special Issue, "Machine Learning and Information Theory", aims to collect recent results in this direction reflecting a diverse spectrum of visions and efforts to extend conventional theories and develop analysis tools for these complex machine learning systems. 2022-10-25T09:04:09Z 2022-10-25T09:04:09Z 2022 book ONIX_20221025_9783036553078_107 9783036553078 9783036553085 https://directory.doabooks.org/handle/20.500.12854/93254 eng application/octet-stream Attribution 4.0 International https://mdpi.com/books/pdfview/book/6152 https://mdpi.com/books/pdfview/book/6152 MDPI - Multidisciplinary Digital Publishing Institute 10.3390/books978-3-0365-5308-5 10.3390/books978-3-0365-5308-5 46cabcaa-dd94-4bfe-87b4-55023c1b36d0 9783036553078 9783036553085 254 open access
spellingShingle supervised classification
independent and non-identically distributed features
analytical error probability
empirical risk
generalization error
K-means clustering
model compression
population risk
rate distortion theory
vector quantization
overfitting
information criteria
entropy
model-based clustering
merging mixture components
component overlap
interpretability
time series prediction
finite state machines
hidden Markov models
recurrent neural networks
reservoir computers
long short-term memory
deep neural network
information theory
local information geometry
feature extraction
spiking neural network
meta-learning
information theoretic learning
minimum error entropy
artificial general intelligence
closed-loop transcription
linear discriminative representation
rate reduction
minimax game
fairness
HGR maximal correlation
independence criterion
separation criterion
pattern dictionary
atypicality
Lempel–Ziv algorithm
lossless compression
anomaly detection
information-theoretic bounds
distribution and federated learning
thema EDItEUR::T Technology, Engineering, Agriculture, Industrial processes::TB Technology: general issues
thema EDItEUR::T Technology, Engineering, Agriculture, Industrial processes::TB Technology: general issues::TBX History of engineering and technology
Information Theory and Machine Learning
title Information Theory and Machine Learning
title_full Information Theory and Machine Learning
title_fullStr Information Theory and Machine Learning
title_full_unstemmed Information Theory and Machine Learning
title_short Information Theory and Machine Learning
title_sort information theory and machine learning
topic supervised classification
independent and non-identically distributed features
analytical error probability
empirical risk
generalization error
K-means clustering
model compression
population risk
rate distortion theory
vector quantization
overfitting
information criteria
entropy
model-based clustering
merging mixture components
component overlap
interpretability
time series prediction
finite state machines
hidden Markov models
recurrent neural networks
reservoir computers
long short-term memory
deep neural network
information theory
local information geometry
feature extraction
spiking neural network
meta-learning
information theoretic learning
minimum error entropy
artificial general intelligence
closed-loop transcription
linear discriminative representation
rate reduction
minimax game
fairness
HGR maximal correlation
independence criterion
separation criterion
pattern dictionary
atypicality
Lempel–Ziv algorithm
lossless compression
anomaly detection
information-theoretic bounds
distribution and federated learning
thema EDItEUR::T Technology, Engineering, Agriculture, Industrial processes::TB Technology: general issues
thema EDItEUR::T Technology, Engineering, Agriculture, Industrial processes::TB Technology: general issues::TBX History of engineering and technology
topic_facet supervised classification
independent and non-identically distributed features
analytical error probability
empirical risk
generalization error
K-means clustering
model compression
population risk
rate distortion theory
vector quantization
overfitting
information criteria
entropy
model-based clustering
merging mixture components
component overlap
interpretability
time series prediction
finite state machines
hidden Markov models
recurrent neural networks
reservoir computers
long short-term memory
deep neural network
information theory
local information geometry
feature extraction
spiking neural network
meta-learning
information theoretic learning
minimum error entropy
artificial general intelligence
closed-loop transcription
linear discriminative representation
rate reduction
minimax game
fairness
HGR maximal correlation
independence criterion
separation criterion
pattern dictionary
atypicality
Lempel–Ziv algorithm
lossless compression
anomaly detection
information-theoretic bounds
distribution and federated learning
thema EDItEUR::T Technology, Engineering, Agriculture, Industrial processes::TB Technology: general issues
thema EDItEUR::T Technology, Engineering, Agriculture, Industrial processes::TB Technology: general issues::TBX History of engineering and technology
url ONIX_20221025_9783036553078_107